How To Setup Enhanced Ecommerce Impressions Using Scroll Tracking

A version of this post originally appeared on Google Analytics Certified Partner InfoTrust's site.

by Nate Denlinger, Web Developer at GACP InfoTrust, LLC

One of our specialities here at InfoTrust is helping ecommerce businesses leverage their web analytics to make better data-driven marketing decisions. This typically starts with installing Google’s Universal Analytics web analytics software and utilizing all of the functionality that is offered with Enhanced Ecommerce tracking capabilities.

Enhanced Ecommerce provides you with a complete picture of what customers on your site are seeing, interacting with and purchasing.

One of the ways you track what your customers are seeing is with product impressions (whenever a user sees an image or description of your products on your website).

Normally, you track what products users see or impressions by simply adding an array of product objects to the DataLayer. These represent the products seen on the page, meaning when any page loads with product images/descriptions, data is sent to Google Analytics that a user saw those specific products. This works well.

However, there is a major issue with this method.  Sometimes you are sending impressions for products that the user never actually sees. This can happen when your page scrolls vertically and some products are off the page or “below the fold”.

For example, lets take a look at a page on Etsy.com:

Sample page on Etsy.com (click for full size)

Here are the results for the search term “Linens”. Currently, you can see sixteen products listed in the search results.  However, in the normal method of sending product impressions, a product impression would be sent for every product on the page.

So, in reality this is what we are telling Google Analytics that the user is seeing (every single product on the page):

Sample page of Etsy.com (click for full-size)

Obviously, no one's screen looks like this, but by sending all products as an impression, we are effectively saying that our customer saw all 63 products. What happens if the user never scrolls past the 16 products shown in the first screenshot?

We are greatly skewing the impressions for the products on the bottom of the page, because often times, users are not scrolling the entire length of the page (and therefore not seeing the additional products).

This could cause you to make incorrect assumptions about how well a product is selling based off of position.

The solution: Scroll-based impression tracking!

Here is how it works at a high level:

1. Instead of automatically adding all product impressions to the DataLayer, we add it to another variable just for temporary storage. Meaning, we do not send all the products loaded on a page directly to Google Analytics, but rather just identify the products that loaded on the page.
2. When the page loads, we actually see what products are visible on the page (ones “above the fold” or where the user can actually see them) and add only those products to the DataLayer for product impressions. Now we don’t send any other product impressions unless they are actually visible to the user.
3. Once the user starts to scroll, we start capturing all the products that haven’t been seen before. We continue to capture these products until the user stops scrolling for a certain amount of time.
4. We then batch all of those products together and send them to the DataLayer as product impressions. 
5. If the user starts to scroll again, we start checking again. However, we never send the same product twice on the same page. If they scroll to the bottom then back up, we don’t send the first products twice.

Using our example on the “Linen” search results, right away we would send product impressions for the first 16 products. Then, let’s say the user scrolled halfway down the page and stopped. We would then send product impressions for products 18 through 40. The user then scrolls to the bottom of the page so we would send product impressions for 41 through 63. Finally the user scrolls back to the top of the page before clicking on the first product. No more impressions would be sent as impressions for all products have already been sent.

The result: Product impressions are only sent as users actually navigate through the pages and can see the products. This is a much more accurate form of product impression tracking since it reflects actual user navigation. 

Next steps: for the technical how-to guide + code samples, please see this post on the InfoTrust site.

Remarketing Lists for Search Ads, Powered by Google Analytics

Today we’re excited to announce you can use audiences (previously remarketing lists) created in Google Analytics to reach your customers on Google Search, with no tagging changes required. 

Remarketing Lists for Search Ads (RLSA) allows you to tailor your search ads and based on your visitors' past activity on your website. Now you can leverage more than 200 Google Analytics dimensions and metrics to create and activate your audiences for remarketing, then use those audiences to reach and re-engage your customers with a consistent message across both Google Search and Display.

TransUnion cuts CPA in half with RLSA

In order to find more customers while reducing waste in their search campaigns, TransUnion, a leading financial services provider, used the audience creation capabilities in Google Analytics to spend more efficiently on Google Search.

TransUnion started by creating two audiences. The first was for new customers―those who had visited the site and started, but not completed a credit application. The other included customers who had already converted. Splitting the audience between new and existing customers allowed TransUnion to bid higher on Google search ads for new customers and spend less on converted customers.

The new RLSA capabilities in Google Analytics yielded impressive conversion rates and cost efficiencies for TransUnion's search campaigns. RLSA visitors had a lower bounce rate and viewed twice as many pages per session compared with regular visitors. 

By using more tailored text with their remarketing lists, TransUnion increased their conversion rate by 65% and average transaction value by 58%. Meanwhile, CPCs for existing customers dropped 50%, resulting in a roughly 50% drop in their cost per transaction. Read the full case study here. 

How to get started

Getting started with RLSA is easier than ever before thanks to Instant Activation. Within the Admin tab, simply click Property, then Tracking Info, and finally Data Collection. Ensure that Remarketing is set to ‘ON.’

Once you’ve enabled this setting, all your eligible audiences will begin to populate for RLSA.

Building Audiences

If you’d like to create new audiences, there are three ways to get started. 

First, you can create a new audience using the Audience builder in the remarketing section of the Admin tab. Make sure you select the relevant AdWords account to share your audience with for remarketing.

If you have an existing segment you’d like to turn into an audience, simply click on the segment options and select “Build Audience” right from within reporting. This option will take you directly to the audience builder as above.  

Finally, you can get started quickly and easily by importing audiences from the Google Analytics Solutions Gallery.

Activating audiences in AdWords

Once you have shared an audience with AdWords, it will appear instantly in your AdWords Shared Library and will show eligible users in the column List size (Google search).  Keep in mind that an audience must accumulate a minimum of 1,000 users before you can use it for remarketing on Google Search. To get started, follow the instructions in the AdWords Help Center. 

Support for RLSA with Google Analytics is part of an ongoing investment to provide powerful ways to activate your customer insights in Google Analytics, along with recent features like Cohort Analysis, Lifetime Value Analysis, and Active User Reporting. Stay tuned for more announcements!

Happy Analyzing,
Lan Huang, Technical Lead, Google Analytics,
Xiaorui Gan, Technical Lead, Google Search Ads

Learn to optimize your tag implementation with Google Tag Manager Fundamentals

We're excited to announce that our next Analytics Academy course, Google Tag Manager Fundamentals, is now open for participation. Whether you’re a marketer, analyst, or developer, this course will teach you how Google Tag Manager can simplify the tag implementation and management process.

You'll join instructor Krista Seiden to explore topics through the lens of a fictional online retailer, The Great Outdoors and their Travel Adventures website. Using practical examples, she’ll show you how to use tools like Google Analytics and Google AdWords tags to improve your data collection process and advertising strategies.

By participating in the course, you’ll explore:

• the core concepts and principles of tag management using Google Tag Manager
• how to create website tags and manage firing triggers
• how to enhance your Google Analytics implementation
• the importance of using the Data Layer to collect valuable data for analysis
• how to configure other marketing tags, like AdWords Conversion Tracking and Dynamic Remarketing

We're looking forward to your participation in this course!

Sign up for Google Tag Manager Fundamentals and start learning today.

Happy tagging!

Post By: Lizzie Pace & The Google Analytics Education Team

Google Computational Journalism Research Awards launch in Europe

Posted by Andrea Held, Google University Relations & Matt Cooke, Google News Lab Europe

Journalism is evolving fast in the digital age, and researchers across Europe are working on exciting projects to create innovative new tools and open source software that will support online journalism and benefit readers. As part of the wider Google Digital News Initiative (DNI), we invited academic researchers across Europe to submit proposals for the Computational Journalism Research Awards.

After careful review by Google’s News Lab and Research teams, the following projects were selected:

SCAN: Systematic Content Analysis of User Comments for Journalists
Walid Maalej, Professor of Informatics, University of Hamburg
Wiebke Loosen, Senior Researcher for Journalism, Hans-Bredow-Institute, Hamburg, Germany
This project aims at developing a framework for the systematic, semi-automated analysis of audience feedback on journalistic content to better reflect the voice of users, mitigate the analysis efforts, and help journalists generate new content from the user comments.

Event Thread Extraction for Viewpoint Analysis
Ioana Manolescu, Senior Researcher, INRIA Saclay, France
Xavier Tannier, Professor of Computer Science, University Paris-Sud, France
The goal of the project is to automatically build topic "event threads" that will help journalists and citizens decode claims made by public figures, in order to distinguish between personal opinion, communication tools and voluntary distortions of the reality.

Computational Support for Creative Story Development by Journalists
Neil Maiden, Professor of Systems Engineering
George Brock, Professor of Journalism, City University London, UK
This project will develop a new software prototype to implement creative search strategies that journalists could use to strengthen investigative storytelling more efficiently than with current news content management and search tools.

We congratulate the recipients of these awards and we look forward to the results of their research. Each award includes funding of up to $60,000 in cash and $20,000 in computing credits on Google’s Cloud Platform. Stay tuned for updates on their progress.

Inceptionism: Going Deeper into Neural Networks

Posted by Alexander Mordvintsev, Software Engineer, Christopher Olah, Software Engineering Intern and Mike Tyka, Software Engineer

Update - 13/07/2015
Images in this blog post are licensed by Google Inc. under a Creative Commons Attribution 4.0 International License. However, images based on places by MIT Computer Science and AI Laboratory require additional permissions from MIT for use.

Artificial Neural Networks have spurred remarkable recent progress in image classification and speech recognition. But even though these are very useful tools based on well-known mathematical methods, we actually understand surprisingly little of why certain models work and others don’t. So let’s take a look at some simple techniques for peeking inside these networks.

We train an artificial neural network by showing it millions of training examples and gradually adjusting the network parameters until it gives the classifications we want. The network typically consists of 10-30 stacked layers of artificial neurons. Each image is fed into the input layer, which then talks to the next layer, until eventually the “output” layer is reached. The network’s “answer” comes from this final output layer.

One of the challenges of neural networks is understanding what exactly goes on at each layer. We know that after training, each layer progressively extracts higher and higher-level features of the image, until the final layer essentially makes a decision on what the image shows. For example, the first layer maybe looks for edges or corners. Intermediate layers interpret the basic features to look for overall shapes or components, like a door or a leaf. The final few layers assemble those into complete interpretations—these neurons activate in response to very complex things such as entire buildings or trees.

One way to visualize what goes on is to turn the network upside down and ask it to enhance an input image in such a way as to elicit a particular interpretation. Say you want to know what sort of image would result in “Banana.” Start with an image full of random noise, then gradually tweak the image towards what the neural net considers a banana (see related work in [1], [2], [3], [4]). By itself, that doesn’t work very well, but it does if we impose a prior constraint that the image should have similar statistics to natural images, such as neighboring pixels needing to be correlated.

So here’s one surprise: neural networks that were trained to discriminate between different kinds of images have quite a bit of the information needed to generate images too. Check out some more examples across different classes:

Why is this important? Well, we train networks by simply showing them many examples of what we want them to learn, hoping they extract the essence of the matter at hand (e.g., a fork needs a handle and 2-4 tines), and learn to ignore what doesn’t matter (a fork can be any shape, size, color or orientation). But how do you check that the network has correctly learned the right features? It can help to visualize the network’s representation of a fork.

Indeed, in some cases, this reveals that the neural net isn’t quite looking for the thing we thought it was. For example, here’s what one neural net we designed thought dumbbells looked like:

There are dumbbells in there alright, but it seems no picture of a dumbbell is complete without a muscular weightlifter there to lift them. In this case, the network failed to completely distill the essence of a dumbbell. Maybe it’s never been shown a dumbbell without an arm holding it. Visualization can help us correct these kinds of training mishaps.

Instead of exactly prescribing which feature we want the network to amplify, we can also let the network make that decision. In this case we simply feed the network an arbitrary image or photo and let the network analyze the picture. We then pick a layer and ask the network to enhance whatever it detected. Each layer of the network deals with features at a different level of abstraction, so the complexity of features we generate depends on which layer we choose to enhance. For example, lower layers tend to produce strokes or simple ornament-like patterns, because those layers are sensitive to basic features such as edges and their orientations.

Left: Original photo by Zachi Evenor. Right: processed by Günther Noack, Software Engineer

Left: Original painting by Georges Seurat. Right: processed images by Matthew McNaughton, Software Engineer

If we choose higher-level layers, which identify more sophisticated features in images, complex features or even whole objects tend to emerge. Again, we just start with an existing image and give it to our neural net. We ask the network: “Whatever you see there, I want more of it!” This creates a feedback loop: if a cloud looks a little bit like a bird, the network will make it look more like a bird. This in turn will make the network recognize the bird even more strongly on the next pass and so forth, until a highly detailed bird appears, seemingly out of nowhere.

The results are intriguing—even a relatively simple neural network can be used to over-interpret an image, just like as children we enjoyed watching clouds and interpreting the random shapes. This network was trained mostly on images of animals, so naturally it tends to interpret shapes as animals. But because the data is stored at such a high abstraction, the results are an interesting remix of these learned features.

Of course, we can do more than cloud watching with this technique. We can apply it to any kind of image. The results vary quite a bit with the kind of image, because the features that are entered bias the network towards certain interpretations. For example, horizon lines tend to get filled with towers and pagodas. Rocks and trees turn into buildings. Birds and insects appear in images of leaves.

The original image influences what kind of objects form in the processed image.

This technique gives us a qualitative sense of the level of abstraction that a particular layer has achieved in its understanding of images. We call this technique “Inceptionism” in reference to the neural net architecture used. See our Inceptionism gallery for more pairs of images and their processed results, plus some cool video animations.

We must go deeper: Iterations

If we apply the algorithm iteratively on its own outputs and apply some zooming after each iteration, we get an endless stream of new impressions, exploring the set of things the network knows about. We can even start this process from a random-noise image, so that the result becomes purely the result of the neural network, as seen in the following images:

Neural net “dreams”— generated purely from random noise, using a network trained on places by MIT Computer Science and AI Laboratory. See our Inceptionism gallery for hi-res versions of the images above and more (Images marked “Places205-GoogLeNet” were made using this network).

The techniques presented here help us understand and visualize how neural networks are able to carry out difficult classification tasks, improve network architecture, and check what the network has learned during training. It also makes us wonder whether neural networks could become a tool for artists—a new way to remix visual concepts—or perhaps even shed a little light on the roots of the creative process in general.

New ways to add Reminders in Inbox by Gmail

Posted by Dave Orr, Google Research Product Manager

Last week, Inbox by Gmail opened up and improved many of your favorite features, including two new ways to add Reminders.

First up, when someone emails you a to-do, Inbox can now suggest adding a Reminder so you don’t forget. Here's how it looks if your spouse emails you and asks you to buy milk on the way home:

To help you add Reminders, the Google Research team used natural language understanding technology to teach Inbox to recognize to-dos in email.

And much like Gmail and Inbox get better when you report spam, your feedback helps improve these suggested Reminders. You can accept or reject them with a single click:

The other new way to add Reminders in Inbox is to create Reminders in Google Keep--they will appear in Inbox with a link back to the full note in Google Keep.

Hopefully, this little extra help gets you back to what matters more quickly and easily. Try the new features out, and as always, let us know what you think using the feedback link in the app.

Google Computer Vision research at CVPR 2015

Posted by Vincent Vanhoucke, Google Research Scientist

Much of the world's data is in the form of visual media. In order to utilize meaningful information from multimedia and deliver innovative products, such as Google Photos, Google builds machine-learning systems that are designed to enable computer perception of visual input, in addition to pursuing image and video analysis techniques focused on image/scene reconstruction and understanding.

This week, Boston hosts the 2015 Conference on Computer Vision and Pattern Recognition (CVPR 2015), the premier annual computer vision event comprising the main CVPR conference and several co-located workshops and short courses. As a leader in computer vision research, Google will have a strong presence at CVPR 2015, with many Googlers presenting publications in addition to hosting workshops and tutorials on topics covering image/video annotation and enhancement, 3D analysis and processing, development of semantic similarity measures for visual objects, synthesis of meaningful composites for visualization/browsing of large image/video collections and more.

Learn more about some of our research in the list below (Googlers highlighted in blue). If you are attending CVPR this year, we hope you’ll stop by our booth and chat with our researchers about the projects and opportunities at Google that go into solving interesting problems for hundreds of millions of people. Members of the Jump team will also have a prototype of the camera on display and will be showing videos produced using the Jump system on Google Cardboard.

Tutorials:
Applied Deep Learning for Computer Vision with Torch
Koray Kavukcuoglu, Ronan Collobert, Soumith Chintala

DIY Deep Learning: a Hands-On Tutorial with Caffe
Evan Shelhamer, Jeff Donahue, Yangqing Jia, Jonathan Long, Ross Girshick

ImageNet Large Scale Visual Recognition Challenge Tutorial
Olga Russakovsky, Jonathan Krause, Karen Simonyan, Yangqing Jia, Jia Deng, Alex Berg, Fei-Fei Li

Fast Image Processing With Halide
Jonathan Ragan-Kelley, Andrew Adams, Fredo Durand

Open Source Structure-from-Motion
Matt Leotta, Sameer Agarwal, Frank Dellaert, Pierre Moulon, Vincent Rabaud

Oral Sessions:
Modeling Local and Global Deformations in Deep Learning: Epitomic Convolution, Multiple Instance Learning, and Sliding Window Detection
George Papandreou, Iasonas Kokkinos, Pierre-André Savalle

Going Deeper with Convolutions
Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich

DynamicFusion: Reconstruction and Tracking of Non-Rigid Scenes in Real-Time
Richard A. Newcombe, Dieter Fox, Steven M. Seitz

Show and Tell: A Neural Image Caption Generator
Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan

Long-Term Recurrent Convolutional Networks for Visual Recognition and Description
Jeffrey Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, Trevor Darrell

Visual Vibrometry: Estimating Material Properties from Small Motion in Video
Abe Davis, Katherine L. Bouman, Justin G. Chen, Michael Rubinstein, Frédo Durand, William T. Freeman

Fast Bilateral-Space Stereo for Synthetic Defocus
Jonathan T. Barron, Andrew Adams, YiChang Shih, Carlos Hernández

Poster Sessions:
Learning Semantic Relationships for Better Action Retrieval in Images
Vignesh Ramanathan, Congcong Li, Jia Deng, Wei Han, Zhen Li, Kunlong Gu, Yang Song, Samy Bengio, Charles Rosenberg, Li Fei-Fei

FaceNet: A Unified Embedding for Face Recognition and Clustering
Florian Schroff, Dmitry Kalenichenko, James Philbin

A Mixed Bag of Emotions: Model, Predict, and Transfer Emotion Distributions
Kuan-Chuan Peng, Tsuhan Chen, Amir Sadovnik, Andrew C. Gallagher

Best-Buddies Similarity for Robust Template Matching
Tali Dekel, Shaul Oron, Michael Rubinstein, Shai Avidan, William T. Freeman

Articulated Motion Discovery Using Pairs of Trajectories
Luca Del Pero, Susanna Ricco, Rahul Sukthankar, Vittorio Ferrari

Reflection Removal Using Ghosting Cues
YiChang Shih, Dilip Krishnan, Frédo Durand, William T. Freeman

P3.5P: Pose Estimation with Unknown Focal Length
Changchang Wu

MatchNet: Unifying Feature and Metric Learning for Patch-Based Matching
Xufeng Han, Thomas Leung, Yangqing Jia, Rahul Sukthankar, Alexander C. Berg

Inferring 3D Layout of Building Facades from a Single Image
Jiyan Pan, Martial Hebert, Takeo Kanade

The Aperture Problem for Refractive Motion
Tianfan Xue, Hossein Mobahei, Frédo Durand, William T. Freeman

Video Magnification in Presence of Large Motions
Mohamed Elgharib, Mohamed Hefeeda, Frédo Durand, William T. Freeman

Robust Video Segment Proposals with Painless Occlusion Handling
Zhengyang Wu, Fuxin Li, Rahul Sukthankar, James M. Rehg

Ontological Supervision for Fine Grained Classification of Street View Storefronts
Yair Movshovitz-Attias, Qian Yu, Martin C. Stumpe, Vinay Shet, Sacha Arnoud, Liron Yatziv

VIP: Finding Important People in Images
Clint Solomon Mathialagan, Andrew C. Gallagher, Dhruv Batra

Fusing Subcategory Probabilities for Texture Classification
Yang Song, Weidong Cai, Qing Li, Fan Zhang

Beyond Short Snippets: Deep Networks for Video Classification
Joe Yue-Hei Ng, Matthew Hausknecht, Sudheendra Vijayanarasimhan, Oriol Vinyals, Rajat Monga, George Toderici

Workshops:
THUMOS Challenge 2015
Program organizers include: Alexander Gorban, Rahul Sukthankar

DeepVision: Deep Learning in Computer Vision 2015
Invited Speaker: Rahul Sukthankar

Large Scale Visual Commerce (LSVisCom)
Panelist: Luc Vincent

Large-Scale Video Search and Mining (LSVSM)
Invited Speaker and Panelist: Rahul Sukthankar
Program Committee includes: Apostol Natsev

Vision meets Cognition: Functionality, Physics, Intentionality and Causality
Program Organizers include: Peter Battaglia

Big Data Meets Computer Vision: 3rd International Workshop on Large Scale Visual Recognition and Retrieval (BigVision 2015)
Program Organizers include: Samy Bengio
Includes speaker Christian Szegedy - “Scalable approaches for large scale vision”

Observing and Understanding Hands in Action (Hands 2015)
Program Committee includes: Murphy Stein

Fine-Grained Visual Categorization (FGVC3)
Program Organizers include: Anelia Angelova

Large-scale Scene Understanding Challenge (LSUN)
Winners of the Scene Classification Challenge: Julian Ibarz, Christian Szegedy and Vincent Vanhoucke
Winners of the Caption Generation Challenge: Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan

Looking from above: when Earth observation meets vision (EARTHVISION)
Technical Committee includes: Andreas Wendel

Computer Vision in Vehicle Technology: Assisted Driving, Exploration Rovers, Aerial and Underwater Vehicles
Invited Speaker: Andreas Wendel
Program Committee includes: Andreas Wendel

Women in Computer Vision (WiCV)
Invited Speaker: Mei Han

ChaLearn Looking at People (sponsor)

Fine-Grained Visual Categorization (FGVC3) (sponsor)

Announcing the 2015 Google European Doctoral Fellows

Posted by David Harper, University Relations and Beate List, Research Programs

In 2009, Google created the PhD Fellowship program to recognize and support outstanding graduate students doing exceptional work in Computer Science and related disciplines. The following year, we launched the program in Europe as the Google European Doctoral Fellowship program. Alumni of the European program occupy a variety of positions including faculty positions (Ofer Meshi, Cynthia Liem), academic research positions (Roland Angst, Carola Doerr née Winzen) and positions in industry (Yair Adato, Peter Hosek, Neil Houlsby).

Reflecting our continuing commitment to building strong relations with the European academic community, we are delighted to announce the 2015 Google European Doctoral Fellows. The following fifteen fellowship recipients were selected from an outstanding set of PhD students nominated by our partner universities:

• Heike Adel, Fellowship in Natural Language Processing (University of Munich)
• Thang Bui, Fellowship in Speech Technology (University of Cambridge)
• Victoria Caparrós Cabezas, Fellowship in Distributed Systems (ETH Zurich)
• Nadav Cohen, Fellowship in Machine Learning (The Hebrew University of Jerusalem)
• Josip Djolonga, Fellowship in Probabilistic Inference (ETH Zurich)
• Jakob Julian Engel, Fellowship in Computer Vision (Technische Universität München)
• Nikola Gvozdiev, Fellowship in Computer Networking (University College London)
• Felix Hill, Fellowship in Language Understanding (University of Cambridge)
• Durk Kingma, Fellowship in Deep Learning (University of Amsterdam)
• Massimo Nicosia, Fellowship in Statistical Natural Language Processing (University of Trento)
• George Prekas, Fellowship in Operating Systems (École Polytechnique Fédérale de Lausanne)
• Roman Prutkin, Fellowship in Graph Algorithms (Karlsruhe Institute of Technology)
• Siva Reddy, Fellowship in Multilingual Semantic Parsing (The University of Edinburgh)
• Immanuel Trummer, Fellowship in Structured Data Analysis (École Polytechnique Fédérale de Lausanne)
• Margarita Vald, Fellowship in Security (Tel Aviv University)

This group of students represent the next generation of researchers who will endeavor to solve some of the most interesting challenges in Computer Science. We offer our congratulations, and look forward to their future contributions to the research community with high expectation.

A Multilingual Corpus of Automatically Extracted Relations from Wikipedia

Posted by Shankar Kumar, Google Research Scientist and Manaal Faruqui, Carnegie Mellon University PhD candidate

In Natural Language Processing, relation extraction is the task of assigning a semantic relationship between a pair of arguments. As an example, a relationship between the phrases “Ottawa” and “Canada” is “is the capital of”. These extracted relations could be used in a variety of applications ranging from Question Answering to building databases from unstructured text.

While relation extraction systems work accurately for English and a few other languages, where tools for syntactic analysis such as parsers, part-of-speech taggers and named entity analyzers are readily available, there is relatively little work in developing such systems for most of the world's languages where linguistic analysis tools do not yet exist. Fortunately, because we do have translation systems between English and many other languages (such as Google Translate), we can translate text from a non-English language to English, perform relation extraction and project these relations back to the foreign language.

Relation extraction in a Spanish sentence using the cross-lingual relation extraction pipeline.

In Multilingual Open Relation Extraction Using Cross-lingual Projection, that will appear at the 2015 Conference of the North American Chapter of the Association for Computational Linguistics – Human Language Technologies (NAACL HLT 2015), we use this idea of cross-lingual projection to develop an algorithm that extracts open-domain relation tuples, i.e. where an arbitrary phrase can describe the relation between the arguments, in multiple languages from Wikipedia. In this work, we also evaluated the performance of extracted relations using human annotations in French, Hindi and Russian.

Since there is no such publicly available corpus of multilingual relations, we are releasing a dataset of automatically extracted relations from the Wikipedia corpus in 61 languages, along with the manually annotated relations in 3 languages (French, Hindi and Russian). It is our hope that our data will help researchers working on natural language processing and encourage novel applications in a wide variety of languages. More details on the corpus and the file formats can be found in this README file.

We wish to thank Bruno Cartoni, Vitaly Nikolaev, Hidetoshi Shimokawa, Kishore Papineni, John Giannandrea and their teams for making this data release possible. This dataset is licensed by Google Inc. under the Creative Commons Attribution-ShareAlike 3.0 License.

BT Increases Sales Volume and Efficiency Using DoubleClick Bid Manager With Google Analytics Premium

Cross-posted on the DoubleClick Advertiser Blog

Modern marketers live in a world that’s dominated by data. Advancements in programmatic buying enable marketers to leverage data and analytics to connect precisely, in real time. Advertisers who are smart about organizing, segmenting, and acting on this data are realizing the benefits of more personalized marketing. BT, a leading telecommunications firm in the UK, did just that and saw fantastic results.  

BT wanted to increase the relevance of their remarketing campaigns by creating more precise audience lists. With the help of their media agency Maxus, BT found that using Google Analytics Premium with DoubleClick Bid Manager offered the ideal solution. 

Google Analytics Premium gave BT the ability to create granular audience segments based on site behavior metrics such as recency, frequency, referral source, and stage of cart abandonment. Once these audience lists were created, the native integration between Google Analytics Premium and DoubleClick Bid Manager meant they could be shared with the platform to make more precise media buys in just a few clicks.

Using Google Analytics Premium with DoubleClick Bid Manager put Maxus and BT in the driver’s seat of their media campaigns. They not only gleaned full transparency with a single customer view and de-duplicated metrics across all channels, but also saw better measurement through unified reporting, and the ability to optimize based on the results.

”Our goals were to build up ‘best practices’ of programmatic display remarketing techniques with a focus on driving post-click sales,” says Alison Thorburn, Head of Digital DR Media at BT. “The DoubleClick suite of products enabled us to do this quickly and efficiently as audience data can be easily organized and utilized.” 

The new analytics-driven approach produced a 69% increase in post-click sales and an 87% reduction in post-click cost per acquisition compared to the previous year’s remarketing activity. It also compared favorably to the remarketing activity that ran simultaneously outside of DoubleClick Bid Manager; post-click sales were 30% higher and post-click cost per acquisition was 42% lower. BT has now consolidated its display remarketing through DoubleClick BidManager.

Read the full case study here.

Posted by-

Kelley Sternhagen, Product Marketing, Google Analytics

Kelly Cox, Product Marketing, DoubleClick